H3 X requires a prompt of 1–7,000 characters; give the action, camera direction and sound, using double quotes for dialogue. For an H3 X sequence, choose 2–15 whole seconds; the default is 5 and the output runs at 24 fps.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- Output7s
rooftop-rain-tango A single quoted line, one slow action and a cut to a close-up in a two-person shot. The prompt also names rain, traffic and a bandoneon; the clip comes back with slow, melancholic music under the line.
- 720p
- 16:9
- 6s
- Output12s
hotel-corridor-three-shots Three shots with start times in a 12-second clip; the cuts came at about 3.9 and 8.3 seconds. Say "same woman in all three shots" so she carries through the cuts. If the picture comes back with black bars, end the prompt with a full-frame 16:9 note.
- 720p
- 16:9
- 12s
- Output5s
lifeguard-tower-dusk A 9:16 prompt for a vertical clip. One person and one gesture keep a short clip steady.
- 720p
- 9:16
- 5s
This example starts at $0.022 per output second. The Playground updates the estimate when you change the settings.